CNN-Based Adversarial Embedding for Image Steganography

You are here

Top Reasons to Join SPS Today!

1. IEEE Signal Processing Magazine
2. Signal Processing Digital Library*
3. Inside Signal Processing Newsletter
4. SPS Resource Center
5. Career advancement & recognition
6. Discounts on conferences and publications
7. Professional networking
8. Communities for students, young professionals, and women
9. Volunteer opportunities
10. Coming soon! PDH/CEU credits
Click here to learn more.

CNN-Based Adversarial Embedding for Image Steganography

By: 
Weixuan Tang; Bin Li; Shunquan Tan; Mauro Barni; Jiwu Huang

Steganographic schemes are commonly designed in a way to preserve image statistics or steganalytic features. Since most of the state-of-the-art steganalytic methods employ a machine learning (ML)-based classifier, it is reasonable to consider countering steganalysis by trying to fool the ML classifiers. However, simply applying perturbations on stego images as adversarial examples may lead to the failure of data extraction and introduce unexpected artifacts detectable by other classifiers. In this paper, we present a steganographic scheme with a novel operation called adversarial embedding (ADV-EMB), which achieves the goal of hiding a stego message while at the same time fooling a convolutional neural network (CNN)-based steganalyzer. The proposed method works under the conventional framework of distortion minimization. In particular, ADV-EMB adjusts the costs of image elements modifications according to the gradients back propagated from the target CNN steganalyzer. Therefore, modification direction has a higher probability to be the same as the inverse sign of the gradient. In this way, the so-called adversarial stego images are generated. Experiments demonstrate that the proposed steganographic scheme achieves better security performance against the target adversary-unaware steganalyzer by increasing its missed detection rate. In addition, it deteriorates the performance of other adversary-aware steganalyzers, opening the way to a new class of modern steganographic schemes capable of overcoming powerful CNN-based steganalysis.

SPS on Twitter

  • The DEGAS Webinar Series continues on Thursday, 2 December when Dr. Michael Schaub presents "Signal processing on g… https://t.co/OwsuUlG2jT
  • Save 50% on IEEE Student Membership to the ultimate network for electrical engineering and computer science student… https://t.co/gutP0cgf4y
  • SPS needs your support! is approaching. If our program receives 30 unique donations of US$10 or… https://t.co/OlN1h1limu
  • On 9 December, the IEEE SPS Sensor Array and Multichannel Technical Committee Webinar Series will feature a talk by… https://t.co/ZptS3D33ij
  • The SPS Webinar Series continues on Friday, 10 December when Dr. Yu Liu presents "Image Fusion with Convolutional S… https://t.co/XhH5XttbsA

SPS Videos


Signal Processing in Home Assistants

 


Multimedia Forensics


Careers in Signal Processing             

 


Under the Radar